minoosh commited on
Commit
8ff6b62
1 Parent(s): a1be7d7

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +26 -26
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 2.8732
20
- - Accuracy: 0.4263
21
 
22
  ## Model description
23
 
@@ -46,33 +46,33 @@ The following hyperparameters were used during training:
46
 
47
  ### Training results
48
 
49
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
- |:-------------:|:-----:|:-----:|:---------------:|:--------:|
51
- | 1.7365 | 1.0 | 502 | 1.5167 | 0.4288 |
52
- | 1.3495 | 2.0 | 1004 | 1.4797 | 0.4592 |
53
- | 1.1131 | 3.0 | 1506 | 1.5093 | 0.4527 |
54
- | 0.9213 | 4.0 | 2008 | 1.6501 | 0.4522 |
55
- | 0.7787 | 5.0 | 2510 | 1.7494 | 0.4407 |
56
- | 0.6594 | 6.0 | 3012 | 1.8600 | 0.4417 |
57
- | 0.5807 | 7.0 | 3514 | 1.9974 | 0.4412 |
58
- | 0.5142 | 8.0 | 4016 | 2.0887 | 0.4273 |
59
- | 0.4716 | 9.0 | 4518 | 2.1556 | 0.4273 |
60
- | 0.4364 | 10.0 | 5020 | 2.2847 | 0.4348 |
61
- | 0.3934 | 11.0 | 5522 | 2.3842 | 0.4298 |
62
- | 0.3774 | 12.0 | 6024 | 2.4663 | 0.4228 |
63
- | 0.3498 | 13.0 | 6526 | 2.5637 | 0.4253 |
64
- | 0.337 | 14.0 | 7028 | 2.6162 | 0.4273 |
65
- | 0.3191 | 15.0 | 7530 | 2.6466 | 0.4268 |
66
- | 0.3081 | 16.0 | 8032 | 2.6214 | 0.4288 |
67
- | 0.2889 | 17.0 | 8534 | 2.8064 | 0.4258 |
68
- | 0.2831 | 18.0 | 9036 | 2.8042 | 0.4228 |
69
- | 0.2733 | 19.0 | 9538 | 2.8510 | 0.4288 |
70
- | 0.2648 | 20.0 | 10040 | 2.8732 | 0.4263 |
71
 
72
 
73
  ### Framework versions
74
 
75
- - Transformers 4.26.0
76
  - Pytorch 1.13.1+cu116
77
- - Datasets 2.9.0
78
  - Tokenizers 0.13.2
 
16
 
17
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 1.0293
20
+ - Accuracy: 0.6664
21
 
22
  ## Model description
23
 
 
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
51
+ | No log | 1.0 | 204 | 1.0807 | 0.6586 |
52
+ | No log | 2.0 | 408 | 1.2250 | 0.6760 |
53
+ | 0.271 | 3.0 | 612 | 1.1975 | 0.6663 |
54
+ | 0.271 | 4.0 | 816 | 1.2170 | 0.6625 |
55
+ | 0.2395 | 5.0 | 1020 | 1.2817 | 0.6702 |
56
+ | 0.2395 | 6.0 | 1224 | 1.4138 | 0.6634 |
57
+ | 0.2395 | 7.0 | 1428 | 1.5268 | 0.6819 |
58
+ | 0.1661 | 8.0 | 1632 | 1.5753 | 0.6702 |
59
+ | 0.1661 | 9.0 | 1836 | 1.6794 | 0.6663 |
60
+ | 0.1349 | 10.0 | 2040 | 1.6416 | 0.6731 |
61
+ | 0.1349 | 11.0 | 2244 | 1.7056 | 0.6741 |
62
+ | 0.1349 | 12.0 | 2448 | 1.7374 | 0.6760 |
63
+ | 0.1159 | 13.0 | 2652 | 1.8817 | 0.6644 |
64
+ | 0.1159 | 14.0 | 2856 | 1.7318 | 0.6751 |
65
+ | 0.111 | 15.0 | 3060 | 1.8213 | 0.6712 |
66
+ | 0.111 | 16.0 | 3264 | 1.8347 | 0.6722 |
67
+ | 0.111 | 17.0 | 3468 | 1.8072 | 0.6780 |
68
+ | 0.0988 | 18.0 | 3672 | 1.8371 | 0.6770 |
69
+ | 0.0988 | 19.0 | 3876 | 1.8562 | 0.6741 |
70
+ | 0.0907 | 20.0 | 4080 | 1.8583 | 0.6741 |
71
 
72
 
73
  ### Framework versions
74
 
75
+ - Transformers 4.26.1
76
  - Pytorch 1.13.1+cu116
77
+ - Datasets 2.10.0
78
  - Tokenizers 0.13.2